caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
dda73336ad22bd0b5ecda17040c50fb10fcbe5fb
clang-p2996/clang/test/CodeGenOpenCL/amdgpu-abi-struct-arg-byref.cl
Nikita Popov 158d72d728 [Clang] Set writable and dead_on_unwind attributes on sret arguments (#77116) 
Set the writable and dead_on_unwind attributes for sret arguments. These
indicate that the argument points to writable memory (and it's legal to
introduce spurious writes to it on entry to the function) and that the
argument memory will not be used if the call unwinds.

This enables additional MemCpyOpt/DSE/LICM optimizations.
2024-01-11 09:46:54 +01:00

300 lines
17 KiB
Common Lisp
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2
// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL2.0 -O0 -triple amdgcn | FileCheck -check-prefix=AMDGCN %s
typedef int int2 __attribute__((ext_vector_type(2)));
typedef struct {
int cells[9];
} Mat3X3;
typedef struct {
int cells[16];
} Mat4X4;
typedef struct {
int cells[1024];
} Mat32X32;
typedef struct {
int cells[4096];
} Mat64X64;
struct StructOneMember {
int2 x;
};
struct StructTwoMember {
int2 x;
int2 y;
};
struct LargeStructOneMember {
int2 x[100];
};
struct LargeStructTwoMember {
int2 x[40];
int2 y[20];
};
#if (__OPENCL_C_VERSION__ == 200) || (__OPENCL_C_VERSION__ >= 300 && defined(__opencl_c_program_scope_global_variables))
struct LargeStructOneMember g_s;
#endif
// AMDGCN-LABEL: define dso_local %struct.Mat4X4 @foo
// AMDGCN-SAME: ([9 x i32] [[IN_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_MAT4X4:%.*]], align 4, addrspace(5)
// AMDGCN-NEXT: [[IN:%.*]] = alloca [[STRUCT_MAT3X3:%.*]], align 4, addrspace(5)
// AMDGCN-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_MAT3X3]], ptr addrspace(5) [[IN]], i32 0, i32 0
// AMDGCN-NEXT: store [9 x i32] [[IN_COERCE]], ptr addrspace(5) [[COERCE_DIVE]], align 4
// AMDGCN-NEXT: [[TMP0:%.*]] = load [[STRUCT_MAT4X4]], ptr addrspace(5) [[RETVAL]], align 4
// AMDGCN-NEXT: ret [[STRUCT_MAT4X4]] [[TMP0]]
//
Mat4X4 __attribute__((noinline)) foo(Mat3X3 in) {
Mat4X4 out;
return out;
}
// Expect two mem copies: one for the argument "in", and one for
// the return value.
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @ker
// AMDGCN-SAME: (ptr addrspace(1) noundef align 4 [[IN:%.*]], ptr addrspace(1) noundef align 4 [[OUT:%.*]]) #[[ATTR1:[0-9]+]] !kernel_arg_addr_space !4 !kernel_arg_access_qual !5 !kernel_arg_type !6 !kernel_arg_base_type !6 !kernel_arg_type_qual !7 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[IN_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// AMDGCN-NEXT: [[OUT_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// AMDGCN-NEXT: [[TMP:%.*]] = alloca [[STRUCT_MAT4X4:%.*]], align 4, addrspace(5)
// AMDGCN-NEXT: store ptr addrspace(1) [[IN]], ptr addrspace(5) [[IN_ADDR]], align 8
// AMDGCN-NEXT: store ptr addrspace(1) [[OUT]], ptr addrspace(5) [[OUT_ADDR]], align 8
// AMDGCN-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[OUT_ADDR]], align 8
// AMDGCN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [[STRUCT_MAT4X4]], ptr addrspace(1) [[TMP0]], i64 0
// AMDGCN-NEXT: [[TMP1:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[IN_ADDR]], align 8
// AMDGCN-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_MAT3X3:%.*]], ptr addrspace(1) [[TMP1]], i64 1
// AMDGCN-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_MAT3X3]], ptr addrspace(1) [[ARRAYIDX1]], i32 0, i32 0
// AMDGCN-NEXT: [[TMP3:%.*]] = load [9 x i32], ptr addrspace(1) [[TMP2]], align 4
// AMDGCN-NEXT: [[CALL:%.*]] = call [[STRUCT_MAT4X4]] @foo([9 x i32] [[TMP3]]) #[[ATTR3:[0-9]+]]
// AMDGCN-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_MAT4X4]], ptr addrspace(5) [[TMP]], i32 0, i32 0
// AMDGCN-NEXT: [[TMP5:%.*]] = extractvalue [[STRUCT_MAT4X4]] [[CALL]], 0
// AMDGCN-NEXT: store [16 x i32] [[TMP5]], ptr addrspace(5) [[TMP4]], align 4
// AMDGCN-NEXT: call void @llvm.memcpy.p1.p5.i64(ptr addrspace(1) align 4 [[ARRAYIDX]], ptr addrspace(5) align 4 [[TMP]], i64 64, i1 false)
// AMDGCN-NEXT: ret void
//
kernel void ker(global Mat3X3 *in, global Mat4X4 *out) {
out[0] = foo(in[1]);
}
// AMDGCN-LABEL: define dso_local void @foo_large
// AMDGCN-SAME: (ptr addrspace(5) dead_on_unwind noalias writable sret([[STRUCT_MAT64X64:%.*]]) align 4 [[AGG_RESULT:%.*]], ptr addrspace(5) noundef byref([[STRUCT_MAT32X32:%.*]]) align 4 [[TMP0:%.*]]) #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[IN:%.*]] = alloca [[STRUCT_MAT32X32]], align 4, addrspace(5)
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[IN]], ptr addrspace(5) align 4 [[TMP0]], i64 4096, i1 false)
// AMDGCN-NEXT: ret void
//
Mat64X64 __attribute__((noinline)) foo_large(Mat32X32 in) {
Mat64X64 out;
return out;
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @ker_large
// AMDGCN-SAME: (ptr addrspace(1) noundef align 4 [[IN:%.*]], ptr addrspace(1) noundef align 4 [[OUT:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !4 !kernel_arg_access_qual !5 !kernel_arg_type !8 !kernel_arg_base_type !8 !kernel_arg_type_qual !7 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[IN_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// AMDGCN-NEXT: [[OUT_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// AMDGCN-NEXT: [[TMP:%.*]] = alloca [[STRUCT_MAT64X64:%.*]], align 4, addrspace(5)
// AMDGCN-NEXT: [[BYVAL_TEMP:%.*]] = alloca [[STRUCT_MAT32X32:%.*]], align 4, addrspace(5)
// AMDGCN-NEXT: store ptr addrspace(1) [[IN]], ptr addrspace(5) [[IN_ADDR]], align 8
// AMDGCN-NEXT: store ptr addrspace(1) [[OUT]], ptr addrspace(5) [[OUT_ADDR]], align 8
// AMDGCN-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[OUT_ADDR]], align 8
// AMDGCN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [[STRUCT_MAT64X64]], ptr addrspace(1) [[TMP0]], i64 0
// AMDGCN-NEXT: [[TMP1:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[IN_ADDR]], align 8
// AMDGCN-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [[STRUCT_MAT32X32]], ptr addrspace(1) [[TMP1]], i64 1
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p1.i64(ptr addrspace(5) align 4 [[BYVAL_TEMP]], ptr addrspace(1) align 4 [[ARRAYIDX1]], i64 4096, i1 false)
// AMDGCN-NEXT: call void @foo_large(ptr addrspace(5) dead_on_unwind writable sret([[STRUCT_MAT64X64]]) align 4 [[TMP]], ptr addrspace(5) noundef byref([[STRUCT_MAT32X32]]) align 4 [[BYVAL_TEMP]]) #[[ATTR3]]
// AMDGCN-NEXT: call void @llvm.memcpy.p1.p5.i64(ptr addrspace(1) align 4 [[ARRAYIDX]], ptr addrspace(5) align 4 [[TMP]], i64 16384, i1 false)
// AMDGCN-NEXT: ret void
//
kernel void ker_large(global Mat32X32 *in, global Mat64X64 *out) {
out[0] = foo_large(in[1]);
}
// AMDGCN-LABEL: define dso_local void @FuncOneMember
// AMDGCN-SAME: (<2 x i32> [[U_COERCE:%.*]]) #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_STRUCTONEMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8, addrspace(5)
// AMDGCN-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_STRUCTONEMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: store <2 x i32> [[U_COERCE]], ptr addrspace(5) [[COERCE_DIVE]], align 8
// AMDGCN-NEXT: store <2 x i32> zeroinitializer, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[TMP0:%.*]] = load <2 x i32>, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[X:%.*]] = getelementptr inbounds [[STRUCT_STRUCTONEMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: store <2 x i32> [[TMP0]], ptr addrspace(5) [[X]], align 8
// AMDGCN-NEXT: ret void
//
void FuncOneMember(struct StructOneMember u) {
u.x = (int2)(0, 0);
}
// AMDGCN-LABEL: define dso_local void @FuncOneLargeMember
// AMDGCN-SAME: (ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTONEMEMBER:%.*]]) align 8 [[TMP0:%.*]]) #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER]], align 8, addrspace(5)
// AMDGCN-NEXT: [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8, addrspace(5)
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 8 [[U]], ptr addrspace(5) align 8 [[TMP0]], i64 800, i1 false)
// AMDGCN-NEXT: store <2 x i32> zeroinitializer, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[TMP1:%.*]] = load <2 x i32>, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[X:%.*]] = getelementptr inbounds [[STRUCT_LARGESTRUCTONEMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x <2 x i32>], ptr addrspace(5) [[X]], i64 0, i64 0
// AMDGCN-NEXT: store <2 x i32> [[TMP1]], ptr addrspace(5) [[ARRAYIDX]], align 8
// AMDGCN-NEXT: ret void
//
void FuncOneLargeMember(struct LargeStructOneMember u) {
u.x[0] = (int2)(0, 0);
}
#if (__OPENCL_C_VERSION__ == 200) || (__OPENCL_C_VERSION__ >= 300 && defined(__opencl_c_program_scope_global_variables))
// AMDGCN-LABEL: define dso_local void @test_indirect_arg_globl
// AMDGCN-SAME: () #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[BYVAL_TEMP:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p1.i64(ptr addrspace(5) align 8 [[BYVAL_TEMP]], ptr addrspace(1) align 8 @g_s, i64 800, i1 false)
// AMDGCN-NEXT: call void @FuncOneLargeMember(ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTONEMEMBER]]) align 8 [[BYVAL_TEMP]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
void test_indirect_arg_globl(void) {
FuncOneLargeMember(g_s);
}
#endif
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @test_indirect_arg_local
// AMDGCN-SAME: () #[[ATTR1]] !kernel_arg_addr_space !9 !kernel_arg_access_qual !9 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !9 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[BYVAL_TEMP:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p3.i64(ptr addrspace(5) align 8 [[BYVAL_TEMP]], ptr addrspace(3) align 8 @test_indirect_arg_local.l_s, i64 800, i1 false)
// AMDGCN-NEXT: call void @FuncOneLargeMember(ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTONEMEMBER]]) align 8 [[BYVAL_TEMP]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void test_indirect_arg_local(void) {
local struct LargeStructOneMember l_s;
FuncOneLargeMember(l_s);
}
// AMDGCN-LABEL: define dso_local void @test_indirect_arg_private
// AMDGCN-SAME: () #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[P_S:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: call void @FuncOneLargeMember(ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTONEMEMBER]]) align 8 [[P_S]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
void test_indirect_arg_private(void) {
struct LargeStructOneMember p_s;
FuncOneLargeMember(p_s);
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @KernelOneMember
// AMDGCN-SAME: (<2 x i32> [[U_COERCE:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !10 !kernel_arg_access_qual !11 !kernel_arg_type !12 !kernel_arg_base_type !12 !kernel_arg_type_qual !13 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_STRUCTONEMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_STRUCTONEMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: store <2 x i32> [[U_COERCE]], ptr addrspace(5) [[COERCE_DIVE]], align 8
// AMDGCN-NEXT: [[COERCE_DIVE1:%.*]] = getelementptr inbounds [[STRUCT_STRUCTONEMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: [[TMP0:%.*]] = load <2 x i32>, ptr addrspace(5) [[COERCE_DIVE1]], align 8
// AMDGCN-NEXT: call void @FuncOneMember(<2 x i32> [[TMP0]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void KernelOneMember(struct StructOneMember u) {
FuncOneMember(u);
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @KernelOneMemberSpir
// AMDGCN-SAME: (ptr addrspace(1) noundef align 8 [[U:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !14 !kernel_arg_access_qual !11 !kernel_arg_type !15 !kernel_arg_base_type !15 !kernel_arg_type_qual !13 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// AMDGCN-NEXT: store ptr addrspace(1) [[U]], ptr addrspace(5) [[U_ADDR]], align 8
// AMDGCN-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[U_ADDR]], align 8
// AMDGCN-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_STRUCTONEMEMBER:%.*]], ptr addrspace(1) [[TMP0]], i32 0, i32 0
// AMDGCN-NEXT: [[TMP1:%.*]] = load <2 x i32>, ptr addrspace(1) [[COERCE_DIVE]], align 8
// AMDGCN-NEXT: call void @FuncOneMember(<2 x i32> [[TMP1]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void KernelOneMemberSpir(global struct StructOneMember* u) {
FuncOneMember(*u);
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @KernelLargeOneMember
// AMDGCN-SAME: ([[STRUCT_LARGESTRUCTONEMEMBER:%.*]] [[U_COERCE:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !10 !kernel_arg_access_qual !11 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !13 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER]], align 8, addrspace(5)
// AMDGCN-NEXT: store [[STRUCT_LARGESTRUCTONEMEMBER]] [[U_COERCE]], ptr addrspace(5) [[U]], align 8
// AMDGCN-NEXT: call void @FuncOneLargeMember(ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTONEMEMBER]]) align 8 [[U]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void KernelLargeOneMember(struct LargeStructOneMember u) {
FuncOneLargeMember(u);
}
// AMDGCN-LABEL: define dso_local void @FuncTwoMember
// AMDGCN-SAME: (<2 x i32> [[U_COERCE0:%.*]], <2 x i32> [[U_COERCE1:%.*]]) #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_STRUCTTWOMEMBER:%.*]], align 8, addrspace(5)
// AMDGCN-NEXT: [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8, addrspace(5)
// AMDGCN-NEXT: [[TMP0:%.*]] = getelementptr inbounds [[STRUCT_STRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: store <2 x i32> [[U_COERCE0]], ptr addrspace(5) [[TMP0]], align 8
// AMDGCN-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_STRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 1
// AMDGCN-NEXT: store <2 x i32> [[U_COERCE1]], ptr addrspace(5) [[TMP1]], align 8
// AMDGCN-NEXT: store <2 x i32> zeroinitializer, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[TMP2:%.*]] = load <2 x i32>, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[Y:%.*]] = getelementptr inbounds [[STRUCT_STRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 1
// AMDGCN-NEXT: store <2 x i32> [[TMP2]], ptr addrspace(5) [[Y]], align 8
// AMDGCN-NEXT: ret void
//
void FuncTwoMember(struct StructTwoMember u) {
u.y = (int2)(0, 0);
}
// AMDGCN-LABEL: define dso_local void @FuncLargeTwoMember
// AMDGCN-SAME: (ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTTWOMEMBER:%.*]]) align 8 [[TMP0:%.*]]) #[[ATTR0]] {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_LARGESTRUCTTWOMEMBER]], align 8, addrspace(5)
// AMDGCN-NEXT: [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8, addrspace(5)
// AMDGCN-NEXT: call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 8 [[U]], ptr addrspace(5) align 8 [[TMP0]], i64 480, i1 false)
// AMDGCN-NEXT: store <2 x i32> zeroinitializer, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[TMP1:%.*]] = load <2 x i32>, ptr addrspace(5) [[DOTCOMPOUNDLITERAL]], align 8
// AMDGCN-NEXT: [[Y:%.*]] = getelementptr inbounds [[STRUCT_LARGESTRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 1
// AMDGCN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [20 x <2 x i32>], ptr addrspace(5) [[Y]], i64 0, i64 0
// AMDGCN-NEXT: store <2 x i32> [[TMP1]], ptr addrspace(5) [[ARRAYIDX]], align 8
// AMDGCN-NEXT: ret void
//
void FuncLargeTwoMember(struct LargeStructTwoMember u) {
u.y[0] = (int2)(0, 0);
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @KernelTwoMember
// AMDGCN-SAME: ([[STRUCT_STRUCTTWOMEMBER:%.*]] [[U_COERCE:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !10 !kernel_arg_access_qual !11 !kernel_arg_type !17 !kernel_arg_base_type !17 !kernel_arg_type_qual !13 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_STRUCTTWOMEMBER]], align 8, addrspace(5)
// AMDGCN-NEXT: store [[STRUCT_STRUCTTWOMEMBER]] [[U_COERCE]], ptr addrspace(5) [[U]], align 8
// AMDGCN-NEXT: [[TMP0:%.*]] = getelementptr inbounds [[STRUCT_STRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 0
// AMDGCN-NEXT: [[TMP1:%.*]] = load <2 x i32>, ptr addrspace(5) [[TMP0]], align 8
// AMDGCN-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_STRUCTTWOMEMBER]], ptr addrspace(5) [[U]], i32 0, i32 1
// AMDGCN-NEXT: [[TMP3:%.*]] = load <2 x i32>, ptr addrspace(5) [[TMP2]], align 8
// AMDGCN-NEXT: call void @FuncTwoMember(<2 x i32> [[TMP1]], <2 x i32> [[TMP3]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void KernelTwoMember(struct StructTwoMember u) {
FuncTwoMember(u);
}
// AMDGCN-LABEL: define dso_local amdgpu_kernel void @KernelLargeTwoMember
// AMDGCN-SAME: ([[STRUCT_LARGESTRUCTTWOMEMBER:%.*]] [[U_COERCE:%.*]]) #[[ATTR1]] !kernel_arg_addr_space !10 !kernel_arg_access_qual !11 !kernel_arg_type !18 !kernel_arg_base_type !18 !kernel_arg_type_qual !13 {
// AMDGCN-NEXT: entry:
// AMDGCN-NEXT: [[U:%.*]] = alloca [[STRUCT_LARGESTRUCTTWOMEMBER]], align 8, addrspace(5)
// AMDGCN-NEXT: store [[STRUCT_LARGESTRUCTTWOMEMBER]] [[U_COERCE]], ptr addrspace(5) [[U]], align 8
// AMDGCN-NEXT: call void @FuncLargeTwoMember(ptr addrspace(5) noundef byref([[STRUCT_LARGESTRUCTTWOMEMBER]]) align 8 [[U]]) #[[ATTR3]]
// AMDGCN-NEXT: ret void
//
kernel void KernelLargeTwoMember(struct LargeStructTwoMember u) {
FuncLargeTwoMember(u);
}
Reference in New Issue View Git Blame Copy Permalink